ML_LOGFILE 0.2.1 * MEMORY INFORMATION *********************************************************************************************************************** Estimated memory consumption for ML force field generation (MB): Persistent allocations for force field : 4725.0 | |-- CMAT for basis : 33.2 |-- FMAT for basis : 4622.4 |-- DESC for basis : 6.2 |-- DESC product matrix : 2.1 Persistent allocations for ab initio data : 90.5 | |-- Ab initio data : 86.8 |-- Ab initio data (new) : 3.7 Temporary allocations for sparsification : 1156.3 | |-- SVD matrices : 1156.1 Other temporary allocations : 65.1 | |-- Descriptors : 16.4 |-- Regression : 30.9 |-- Prediction : 17.8 Total memory consumption : 6036.8 ******************************************************************************************************************************************** * MACHINE LEARNING SETTINGS **************************************************************************************************************** This section lists the available machine-learning related settings with a short description, their selected values and the INCAR tags. The column between the value and the INCAR tag may contain a "state indicator" highlighting the origin of the value. Here is a list of possible indicators: * : (empty) Tag was not provided in the INCAR file, a default value was chosen automatically. * (I) : Value was provided in the INCAR file. * (i) : Value was provided in the INCAR file, deprecated tag. * (!) : A value found in the INCAR file was overwritten by the contents of the ML_FF or ML_AB file. * (?) : The value for this tag was never set (please report this to the VASP developers). Tag values with associated units are given here in Angstrom/eV, if not specified otherwise. Please refer to the VASP online manual for a detailed description of available INCAR tags. General settings -------------------------------------------------------------------------------------------------------------------------------------------- Machine learning operation mode in strings (supertag) : NONE ML_MODE Machine learning operation mode : 0 (I) ML_ISTART Precontraction of weights on Kernel for fast execution (ML_ISTART=2 only), but no error estimation : F ML_LFAST Controls the verbosity of the output at each MD step when machine learning is used : 1 ML_OUTPUT_MODE Sets the output frequency at various places for ML_ISTART=2 : 1 ML_OUTBLOCK Descriptor settings -------------------------------------------------------------------------------------------------------------------------------------------- Radial descriptors: ------------------- Cutoff radius of radial descriptors : 8.00000E+00 ML_RCUT1 Gaussian width for broadening the atomic distribution for radial descriptors : 5.00000E-01 ML_SION1 Number of radial basis functions for atomic distribution for radial descriptors : 12 ML_MRB1 Angular descriptors: -------------------- Descriptor type (standard, linear-scaling with element types, ...) : 0 ML_DESC_TYPE Cutoff radius of angular descriptors : 5.00000E+00 ML_RCUT2 Gaussian width for broadening the atomic distribution for angular descriptors : 5.00000E-01 ML_SION2 Number of radial basis functions for atomic distribution for angular descriptors : 8 ML_MRB2 Maximum angular momentum quantum number of spherical harmonics used to expand atomic distributions : 3 ML_LMAX2 Angular filtering enabled : T ML_LAFILT2 Angular filtering parameter a_FILT : 2.00000E-03 ML_AFILT2 Angular filtering function type : 2 ML_IAFILT2 Enable sparsification of angular descriptors : F ML_LSPARSDES Number of highest eigenvalues relevant in the sparsification algorithm of the angular descriptors : 5 ML_NRANK_SPARSDES Desired ratio of selected to all descriptors resulting from the angular descriptor sparsification : 5.00000E-01 ML_RDES_SPARSDES Kernel settings -------------------------------------------------------------------------------------------------------------------------------------------- Weight of radial descriptors in the kernel (the angular counterpart is chosen so that the sum is 1.0) : 1.00000E-01 ML_W1 Power of the polynomial kernel : 4 ML_NHYP Specifies whether super-vector is used for kernel or not : T ML_LSUPERVEC Bayesian error estimation -------------------------------------------------------------------------------------------------------------------------------------------- Enable automatic updating of the Bayesian error estimation threshold during on-the-fly training : 1 ML_ICRITERIA Decides whether update of threshold is done in the same MD step or the next MD step : 1 ML_IUPDATE_CRITERIA Bayesian error estimation threshold (initial or static value depending on other settings) : 2.00000E-03 ML_CTIFOR Scaling factor for ML_CTIFOR. The interval 0